paper-with-me

Papers

When is Trust Robust?

2024-03-19 · Luca Anderlini, Larry Samuelson, Daniele Terlizzese

We examine an economy in which interactions are more productive if agents can trust others to refrain from cheating. Some agents are scoundrels, who cheat at every opportunity, while others cheat only if the cost of cheating, a decreasing function of the proportion of cheaters, is sufficiently low. The economy exhibits multiple equilibria. As the proportion of scoundrels in the economy declines, the high-trust equilibrium can be disrupted by arbitrarily small perturbations or by arbitrarily small infusions of low-trust agents, while the low-trust equilibrium becomes impervious to perturbations and infusions of high-trust agents. Scoundrels may thus have the effect of making trust more robust.

📄 PDF Abstract BibTeX arXiv:2403.12917

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Citations and Trust in LLM Generated Responses

2025-01-02 · Yifan Ding, Matthew Facciani, Amrit Poudel, Ellen Joyce 외

Question answering systems are rapidly advancing, but their opaque nature may impact user trust. We explored trust through an anti-monitoring framework, where trust is predicted to be correlated with presence of citation…

ChatbotQuestion Answering

When Robots Say No: Temporal Trust Recovery Through Explanation

2025-09-15 · Nicola Webb, Zijun Huang, Sanja Milivojevic, Chris Baber 외 arxiv

Mobile robots with some degree of autonomy could deliver significant advantages in high-risk missions such as search and rescue and firefighting. Integrated into a human-robot team (HRT), robots could work effectively to…

Measuring an artificial intelligence agent's trust in humans using machine incentives

2022-12-27 · Tim Johnson, Nick Obradovich

Scientists and philosophers have debated whether humans can trust advanced artificial intelligence (AI) agents to respect humanity's best interests. Yet what about the reverse? Will advanced AI agents trust humans? Gaugi…

AI AgentLanguage ModellingLarge Language Model

Can a Robot Trust You? A DRL-Based Approach to Trust-Driven Human-Guided Navigation

2020-11-01 · Vishnu Sashank Dorbala, Arjun Srinivasan, Aniket Bera

Humans are known to construct cognitive maps of their everyday surroundings using a variety of perceptual inputs. As such, when a human is asked for directions to a particular location, their wayfinding capability in con…

Deep Reinforcement LearningNavigateRobot Navigation

Why Would You Suggest That? Human Trust in Language Model Responses

2024-06-04 · Manasi Sharma, Ho Chit Siu, Rohan Paleja, Jaime D. Peña

The emergence of Large Language Models (LLMs) has revealed a growing need for human-AI collaboration, especially in creative decision-making scenarios where trust and reliance are paramount. Through human studies and mod…

Decision MakingHeadline GenerationLanguage ModelingLanguage Modelling